Blog
Deep-dives, releases, and self-host stories.
deputyOS release notes, design decisions, and deep-dives on local-first AI. Articles for self-hosters, makers, and engineers.
-
-
-
6 min readHow deputyOS images are signed (minisign + cosign + SLSA)
The full trust chain for an deputyOS image: how it's built reproducibly, signed twice, attested, and verified at apply time.
-
6 min readLFM2 explained: why we picked Liquid AI's models for the air-gapped tier
Why deputyOS bakes LFM2 instead of Llama or Phi for the air-gapped tier, what trade-offs we made, and what you actually get.
-
4 min readCheap AI on Hetzner: cloud-init recipe walkthrough
Run deputyOS on a €4 Hetzner cloud server. Cloud-init recipe, no image transfer needed, ready in under 5 minutes.
-
6 min readSpin up deputyOS on DigitalOcean in 4 minutes
End-to-end DigitalOcean walkthrough: create a $4 droplet, paste the snapshot, point your channels at the public IP, done.
-
6 min readPi 5 vs x86 mini-PC for self-hosted AI: a real-numbers comparison
Real benchmarks on real hardware: Pi 5 8/16 GB vs Beelink-class x86 mini-PCs for running a self-hosted AI assistant.
-
6 min readA ChatGPT alternative you run yourself, in 2026
Why and how to replace ChatGPT with a self-hosted AI assistant on hardware you own — without giving up the things that make ChatGPT useful.
-
